ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

OBJECTIVE: To investigate the anti-tumor effects of cinobufacini (CINO) on hepatocellular carcinoma (HCC) induced by des-gamma-carboxy-prothrombin (DCP) and to uncover the underlying mechanisms. METHODS: The inhibitory effect of CINO on HCC cell proliferation was evaluated using the cell counting kit-8 method, and the apoptosis rate was quantified using flow cytometry. Immunofluorescence and Western blot analyses were used to investigate the differential expression of proteins associated with cell growth, apoptosis, migration, and invasion pathways after CINO treatment. The therapeutic potential of CINO for HCC was confirmed, and the possibility of combining cinobufacini with c-Met inhibitor for the treatment of primary HCC was further validated by in vivo experiments. RESULTS: Under the induction of DCP, CINO inhibited the activity of HCC cells, induced apoptosis, and inhibited migration and invasion. Upon the induction of DCP, CINO regulated c-Met activation and the activation of the phosphatidylinositol-3 kinase/protein kinase B (PI3K/AKT) and mitogen-activated protein kinase kinase/extracellular signal-regulated kinase (MEK/ERK) pathways. In a mouse model of HCC, CINO exhibited significant antitumor effects by inhibiting the phosphorylation of c-Met and the downstream PI3K/AKT and MEK/ERK pathways in tumor tissues. CONCLUSIONS CINO inhibited HCC cell growth, promoted apoptosis, and suppressed HCC cell invasion and migration by targeting c-Met and PI3K/AKT and MEK/ERK signaling pathways under DCP induction.
Carcinoma, Hepatocellular/drug therapy* ; Proto-Oncogene Proteins c-met/metabolism* ; Liver Neoplasms/drug therapy* ; Signal Transduction/drug effects* ; Animals ; Humans ; Cell Movement/drug effects* ; Apoptosis/drug effects* ; Cell Proliferation/drug effects* ; Amphibian Venoms/therapeutic use* ; Cell Line, Tumor ; Neoplasm Metastasis ; Cell Survival/drug effects* ; Proto-Oncogene Proteins c-akt/metabolism* ; Phosphatidylinositol 3-Kinases/metabolism* ; Neoplasm Invasiveness ; Mice, Inbred BALB C ; Mice, Nude ; Mice ; Male ; Bufanolides/therapeutic use* ; Protein Precursors ; Prothrombin ; Biomarkers

OBJECTIVE: To explore the efficacy and safety of Juan Bi Pill (JBP) in treatment of active rheumatoid arthritis (RA). METHODS: From February 2017 to May 2018, 115 participants from 4 centers were randomly divided into JBP group (57 cases) and placebo group (58 cases) in a 1:1 ratio using a random number table method. Participants received a dose of JBP (4 g, twice a day, orally) combined with methotrexate (MTX, 10 mg per week) or placebo (4 g, twice a day, orally) combined with MTX for 12 weeks. Participants were required with follow-up visits at 24 and 48 weeks, attending 7 assessment visits. Participants were undergo disease activity assessment 7 times (at baseline and 2, 4, 8, 12, 24, 48 weeks) and safety assessments 6 times (at baseline and 4, 8, 12, 24, 48 weeks). The primary endpoint was 28-joint Disease Activity Score (DAS28-ESR and DAS28-CRP). The secondary endpoints included American College of Rheumatology (ACR) criteria for 20% and 50% improvement (ACR20/50), Health Assessment Questionnaire Disability Index (HAQ-DI), clinical disease activity index (CDAI), visual analog scale (VAS), Short Form-36 (SF-36) score, Medial Outcomes Study (MOS) sleep scale score, serum erythrocyte sedimentation rate (ESR), C-reactive protein (CRP), tender joint count, swollen joint count, and morning stiffness. The adverse reactions were observed during the treatment. RESULTS: After 12 weeks of treatment, DAS28-ESR and DAS28-CRP scores in both groups were lower than before treatment (both P<0.01), while the remission rate of DAS28-ESR and DAS28-CRP and low disease activity of JBP group were higher than those in the placebo group (both P<0.01). JBP demonstrated better efficacy on ACR20 and ACR50 compliance rate at 12 and 48 weeks comparing to placebo (all P<0.05). The CDAI and HAQ-DI score, pain VAS and global VAS change of RA patients and physicians, the serum ESR and CRP levels, and the number of tenderness and swelling joints were lower than before treatment at 4, 8, 12, 24, 48 weeks in both groups (P<0.05 or P<0.01), while the reduction of above indices in the JBP group was more obvious than those in the placebo group at 12 weeks (ESR and CRP, both P<0.05) or at 12 and 48 weeks (all P<0.01). There was no difference in adverse reactions between the 2 groups during treatment (P=0.75). CONCLUSION JBP combined with MTX could effectively reduce disease activity in patients with RA in active stage, reduce the symptoms of arthritis, and improve the quality of life, while ensuring safety, reliability, and fewer adverse effects. (Trial Registration: ClinicalTrials.gov, No. NCT02885597).
Humans ; Arthritis, Rheumatoid/drug therapy* ; Methotrexate/adverse effects* ; Female ; Double-Blind Method ; Male ; Middle Aged ; Treatment Outcome ; Drugs, Chinese Herbal/adverse effects* ; Drug Therapy, Combination ; Adult ; Antirheumatic Agents/adverse effects* ; Aged

Traditional Chinese medicine (TCM) represents a paradigmatic approach to personalized medicine, developed through the systematic accumulation and refinement of clinical empirical data over more than 2000 years, and now encompasses large-scale electronic medical records (EMR) and experimental molecular data. Artificial intelligence (AI) has demonstrated its utility in medicine through the development of various expert systems (e.g., MYCIN) since the 1970s. With the emergence of deep learning and large language models (LLMs), AI's potential in medicine shows considerable promise. Consequently, the integration of AI and TCM from both clinical and scientific perspectives presents a fundamental and promising research direction. This survey provides an insightful overview of TCM AI research, summarizing related research tasks from three perspectives: systems-level biological mechanism elucidation, real-world clinical evidence inference, and personalized clinical decision support. The review highlights representative AI methodologies alongside their applications in both TCM scientific inquiry and clinical practice. To critically assess the current state of the field, this work identifies major challenges and opportunities that constrain the development of robust research capabilities-particularly in the mechanistic understanding of TCM syndromes and herbal formulations, novel drug discovery, and the delivery of high-quality, patient-centered clinical care. The findings underscore that future advancements in AI-driven TCM research will rely on the development of high-quality, large-scale data repositories; the construction of comprehensive and domain-specific knowledge graphs (KGs); deeper insights into the biological mechanisms underpinning clinical efficacy; rigorous causal inference frameworks; and intelligent, personalized decision support systems.
Medicine, Chinese Traditional/methods* ; Artificial Intelligence ; Humans ; Precision Medicine ; Decision Support Systems, Clinical

OBJECTIVE: To investigate chronic hepatitis C virus (HCV) infection's effect on gestational liver function, pregnancy and delivery complications, and neonatal development. METHODS: A total of 157 HCV antibody-positive (anti-HCV[+]) and HCV RNA(+) patients (Group C) and 121 anti-HCV(+) and HCV RNA(-) patients (Group B) were included as study participants, while 142 anti-HCV(-) and HCV RNA(-) patients (Group A) were the control group. Data on biochemical indices during pregnancy, pregnancy complications, delivery-related information, and neonatal complications were also collected. RESULTS: Elevated alanine aminotransferase (ALT) rates in Group C during early, middle, and late pregnancy were 59.87%, 43.95%, and 42.04%, respectively-significantly higher than Groups B (26.45%, 15.70%, 10.74%) and A (23.94%, 19.01%, 6.34%) ( P < 0.05). Median ALT levels in Group C were significantly higher than in Groups A and B at all pregnancy stages ( P < 0.05). No significant differences were found in neonatal malformation rates across groups ( P > 0.05). However, neonatal jaundice incidence was significantly greater in Group C (75.16%) compared to Groups A (42.25%) and B (57.02%) ( χ ² = 33.552, P < 0.001). HCV RNA positivity during pregnancy was an independent risk factor for neonatal jaundice ( OR = 2.111, 95% CI 1.242-3.588, P = 0.006). CONCLUSIONS Chronic HCV infection can affect the liver function of pregnant women, but does not increase the pregnancy or delivery complication risks. HCV RNA(+) is an independent risk factor for neonatal jaundice.
Humans ; Female ; Pregnancy ; Adult ; Pregnancy Complications, Infectious/epidemiology* ; Retrospective Studies ; Pregnancy Outcome ; Infant, Newborn ; Viremia/virology* ; Hepatitis C ; Hepacivirus/physiology* ; Hepatitis C, Chronic/virology* ; Young Adult ; Alanine Transaminase/blood*

OBJECTIVE: To investigate the association between long-term glycemic control and cerebral infarction risk in patients with diabetes through a large-scale cohort study. METHODS: This prospective, community-based cohort study included 12,054 patients with diabetes. From 2006 to 2012, 38,272 fasting blood glucose (FBG) measurements were obtained from these participants. FBG trajectory patterns were generated using latent mixture modelling. Cox proportional hazards models were applied to assess the subsequent risk of cerebral infarction associated with different FBG trajectory patterns. RESULTS: At baseline, the mean age of the participants was 55.2 years. Four distinct FBG trajectories were identified based on FBG concentrations and their changes over the 6-year follow-up period. After a median follow-up of 6.9 years, 786 cerebral infarction events were recorded. Different trajectory patterns were associated with significantly varied outcome risks (Log-Rank P < 0.001). Compared with the low-stability group, Hazard Ratio ( HR) adjusted for potential confounders were 1.37 for the moderate-increasing group, 1.23 for the elevated-decreasing group, and 2.08 for the elevated-stable group. CONCLUSION Sustained high FBG levels were found to play a critical role in the development of ischemic stroke among patients with diabetes. Controlling FBG levels may reduce the risk of cerebral infarction.
Humans ; Cerebral Infarction/blood* ; Middle Aged ; Male ; Female ; Blood Glucose/analysis* ; Fasting/blood* ; Aged ; Prospective Studies ; Risk Factors ; Diabetes Mellitus/blood* ; Adult ; Proportional Hazards Models

ObjectivePrimary liver cancer, predominantly hepatocellular carcinoma (HCC), is a significant global health issue, ranking as the sixth most diagnosed cancer and the third leading cause of cancer-related mortality. Accurate and early diagnosis of HCC is crucial for effective treatment, as HCC and non-HCC malignancies like intrahepatic cholangiocarcinoma (ICC) exhibit different prognoses and treatment responses. Traditional diagnostic methods, including liver biopsy and contrast-enhanced ultrasound (CEUS), face limitations in applicability and objectivity. The primary objective of this study was to develop an advanced, light-weighted classification network capable of distinguishing HCC from other non-HCC malignancies by leveraging the automatic analysis of brightness changes in CEUS images. The ultimate goal was to create a user-friendly and cost-efficient computer-aided diagnostic tool that could assist radiologists in making more accurate and efficient clinical decisions. MethodsThis retrospective study encompassed a total of 161 patients, comprising 131 diagnosed with HCC and 30 with non-HCC malignancies. To achieve accurate tumor detection, the YOLOX network was employed to identify the region of interest (ROI) on both B-mode ultrasound and CEUS images. A custom-developed algorithm was then utilized to extract brightness change curves from the tumor and adjacent liver parenchyma regions within the CEUS images. These curves provided critical data for the subsequent analysis and classification process. To analyze the extracted brightness change curves and classify the malignancies, we developed and compared several models. These included one-dimensional convolutional neural networks (1D-ResNet, 1D-ConvNeXt, and 1D-CNN), as well as traditional machine-learning methods such as support vector machine (SVM), ensemble learning (EL), k-nearest neighbor (KNN), and decision tree (DT). The diagnostic performance of each method in distinguishing HCC from non-HCC malignancies was rigorously evaluated using four key metrics: area under the receiver operating characteristic (AUC), accuracy (ACC), sensitivity (SE), and specificity (SP). ResultsThe evaluation of the machine-learning methods revealed AUC values of 0.70 for SVM, 0.56 for ensemble learning, 0.63 for KNN, and 0.72 for the decision tree. These results indicated moderate to fair performance in classifying the malignancies based on the brightness change curves. In contrast, the deep learning models demonstrated significantly higher AUCs, with 1D-ResNet achieving an AUC of 0.72, 1D-ConvNeXt reaching 0.82, and 1D-CNN obtaining the highest AUC of 0.84. Moreover, under the five-fold cross-validation scheme, the 1D-CNN model outperformed other models in both accuracy and specificity. Specifically, it achieved accuracy improvements of 3.8% to 10.0% and specificity enhancements of 6.6% to 43.3% over competing approaches. The superior performance of the 1D-CNN model highlighted its potential as a powerful tool for accurate classification. ConclusionThe 1D-CNN model proved to be the most effective in differentiating HCC from non-HCC malignancies, surpassing both traditional machine-learning methods and other deep learning models. This study successfully developed a user-friendly and cost-efficient computer-aided diagnostic solution that would significantly enhances radiologists’ diagnostic capabilities. By improving the accuracy and efficiency of clinical decision-making, this tool has the potential to positively impact patient care and outcomes. Future work may focus on further refining the model and exploring its integration with multimodal ultrasound data to maximize its accuracy and applicability.

Objective:This study aimed to validated the diagnostic accuracy of Global Leadership Initiative on Malnutrition(GLIM)criteria for malnutrition in pancreatic cancer patients undergoing pancreaticoduodenectomy and to evaluated its prognostic value for postoperative outcome.Methods:A retrospective analysis was conducted on 230 consecutive pancreatic cancer patients who underwent pancreaticoduodenectomy at the Department of Pancreatobiliary Surgery,Sun Yat-sen University Cancer Center,between January 2018 to January 2024.Patients were stratified into malnutrition group and non-malnutrition group using Nutritional Risk Screening 2002(NRS 2002)and GLIM criteria.Multivariable logistic regression identified independent risk factors for postoperative morbidity.Results:GLIM criteria identified malnutrition in 96 patients(41.7％).Compared with the non-malnourished group,the number of preoperative nutritional support(t=20.038,P<0.001),the number of preoperative enteral nutrition support(t=8.377,P=0.004),the number of preoperative parenteral nutrition support(t=22.302,P<0.001),the number of anemia(t=8.037,P=0.005)and preoperative parenteral nutrition use days(t=-2.898,P=0.009),the difference was statistically significant.There were statistically significant differences in C-reactive protein(t=10.944,P=0.008),NLR(t=-2.523,P=0.012)and PNI(t=-2.397,P=0.017)between the two groups before surgery.Preoperative BMI(t=-4.410,P<0.001)was significantly lower in the malnourished group.The number of postoperative parenteral nutrition days(Z=-2.283,P=0.022)and amino acid supplementation during postoperative hospitalization were significantly higher in the malnourished group(Z=-2.309,P=0.021).The incidence of malnutrition was higher in patients with Clavien-Dindo grade≥Ⅲ(P=0.030)and intra-abdominal infections(P=0.049).Multivariable analysis identified preoperative weight loss(OR=2.154,95％CI:1.158～4.005;P=0.015)and BMI reduction(OR=0.175,95％CI:0.040～0.775;P=0.022)as independent predictors of postoperative complications.Conclusions:The GLIM standard effectively characterize malnutrition status in pancreatic cancer patients after pancreaticoduodenectomy patients and demonstrate superior predictive performance for postoperative morbidity.It has good predictive performance and clinical application value.

BACKGROUND: Disease-modifying therapies have been approved for the treatment of relapsing multiple sclerosis (RMS). The present study aims to examine the safety of teriflunomide in Chinese patients with RMS. METHODS: This non-randomized, multi-center, 24-week, prospective study enrolled RMS patients with variant (c.421C>A) or wild type ABCG2 who received once-daily oral teriflunomide 14 mg. The primary endpoint was the relationship between ABCG2 polymorphisms and teriflunomide exposure over 24 weeks. Safety was assessed over the 24-week treatment with teriflunomide. RESULTS: Eighty-two patients were assigned to variant ( n  = 42) and wild type groups ( n  = 40), respectively. Geometric mean and geometric standard deviation (SD) of pre-dose concentration (variant, 54.9 [38.0] μg/mL; wild type, 49.1 [32.0] μg/mL) and area under plasma concentration-time curve over a dosing interval (AUC tau ) (variant, 1731.3 [769.0] μg∙h/mL; wild type, 1564.5 [1053.0] μg∙h/mL) values at steady state were approximately similar between the two groups. Safety profile was similar and well tolerated across variant and wild type groups in terms of rates of treatment emergent adverse events (TEAE), treatment-related TEAE, grade ≥3 TEAE, and serious adverse events (AEs). No new specific safety concerns or deaths were reported in the study. CONCLUSION: ABCG2 polymorphisms did not affect the steady-state exposure of teriflunomide, suggesting a similar efficacy and safety profile between variant and wild type RMS patients. REGISTRATION NCT04410965, https://clinicaltrials.gov .
Humans ; Crotonates/adverse effects* ; Toluidines/adverse effects* ; Nitriles ; Hydroxybutyrates ; Female ; Male ; Adult ; ATP Binding Cassette Transporter, Subfamily G, Member 2/genetics* ; Middle Aged ; Multiple Sclerosis, Relapsing-Remitting/genetics* ; Prospective Studies ; Young Adult ; Neoplasm Proteins/genetics* ; East Asian People